Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2304.12890 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909401618579456 |
|---|---|
| author | Shafique, Muhammad Liu, Sizhuo Schniter, Philip Ahmad, Rizwan |
| author_facet | Shafique, Muhammad Liu, Sizhuo Schniter, Philip Ahmad, Rizwan |
| contents | Objective: Acquiring fully sampled training data is challenging for many MRI applications. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recovering images solely from undersampled data.
Materials and Methods: ReSiDe is inspired by plug-and-play (PnP) methods, but unlike traditional PnP approaches that utilize pre-trained denoisers, ReSiDe iteratively trains the denoiser on the image or images that are being reconstructed. We introduce two variations of our method: ReSiDe-S and ReSiDe-M. ReSiDe-S is scan-specific and works with a single set of undersampled measurements, while ReSiDe-M operates on multiple sets of undersampled measurements and provides faster inference. Studies I, II, and III compare ReSiDe-S and ReSiDe-M against other self-supervised or unsupervised methods using data from T1- and T2-weighted brain MRI, MRXCAT digital perfusion phantom, and first-pass cardiac perfusion, respectively.
Results: ReSiDe-S and ReSiDe-M outperform other methods in terms of peak signal-to-noise ratio and structural similarity index measure for Studies I and II, and in terms of expert scoring for Study III.
Discussion: We present a self-supervised image reconstruction method and validate it in both static and dynamic MRI applications. These developments can benefit MRI applications where the availability of fully sampled training data is limited. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_12890 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data Shafique, Muhammad Liu, Sizhuo Schniter, Philip Ahmad, Rizwan Image and Video Processing Objective: Acquiring fully sampled training data is challenging for many MRI applications. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recovering images solely from undersampled data. Materials and Methods: ReSiDe is inspired by plug-and-play (PnP) methods, but unlike traditional PnP approaches that utilize pre-trained denoisers, ReSiDe iteratively trains the denoiser on the image or images that are being reconstructed. We introduce two variations of our method: ReSiDe-S and ReSiDe-M. ReSiDe-S is scan-specific and works with a single set of undersampled measurements, while ReSiDe-M operates on multiple sets of undersampled measurements and provides faster inference. Studies I, II, and III compare ReSiDe-S and ReSiDe-M against other self-supervised or unsupervised methods using data from T1- and T2-weighted brain MRI, MRXCAT digital perfusion phantom, and first-pass cardiac perfusion, respectively. Results: ReSiDe-S and ReSiDe-M outperform other methods in terms of peak signal-to-noise ratio and structural similarity index measure for Studies I and II, and in terms of expert scoring for Study III. Discussion: We present a self-supervised image reconstruction method and validate it in both static and dynamic MRI applications. These developments can benefit MRI applications where the availability of fully sampled training data is limited. |
| title | MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2304.12890 |